![[2602.19411] MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.19411] MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry
Summary
The paper presents MACE-POLAR-1, a new electrostatic foundation model for molecular chemistry that improves the accuracy of modeling long-range electrostatic interactions and charge transfer, enhancing computational efficiency and versatility in drug discovery.
Why It Matters
This research addresses a significant limitation in current machine learning interatomic potentials, which often fail to accurately model long-range electrostatic effects. By introducing MACE-POLAR-1, the authors provide a more robust tool for computational chemistry, potentially impacting drug discovery and materials science.
Key Takeaways
- MACE-POLAR-1 effectively models long-range electrostatic interactions.
- The model shows competitive accuracy with hybrid DFT methods across various chemical benchmarks.
- It significantly improves predictions of non-covalent interactions and molecular crystal formation energies.
- The approach allows for variable charge and spin state handling, enhancing its applicability.
- MACE-POLAR-1 is positioned as a versatile tool for computational molecular chemistry.
Physics > Chemical Physics arXiv:2602.19411 (physics) [Submitted on 23 Feb 2026] Title:MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry Authors:Ilyes Batatia, William J. Baldwin, Domantas Kuryla, Joseph Hart, Elliott Kasoar, Alin M. Elena, Harry Moore, Mikołaj J. Gawkowski, Benjamin X. Shi, Venkat Kapil, Panagiotis Kourtis, Ioan-Bogdan Magdău, Gábor Csányi View a PDF of the paper titled MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry, by Ilyes Batatia and 11 other authors View PDF HTML (experimental) Abstract:Accurate modelling of electrostatic interactions and charge transfer is fundamental to computational chemistry, yet most machine learning interatomic potentials (MLIPs) rely on local atomic descriptors that cannot capture long-range electrostatic effects. We present a new electrostatic foundation model for molecular chemistry that extends the MACE architecture with explicit treatment of long-range interactions and electrostatic induction. Our approach combines local many-body geometric features with a non-self-consistent field formalism that updates learnable charge and spin densities through polarisable iterations to model induction, followed by global charge equilibration via learnable Fukui functions to control total charge and total spin. This design enables an accurate and physical description of systems with varying charge and spin states while maintaining computational efficiency. Trained on t...
